Budgets & Limits for every API key.

Set per-key spend caps with automatic reset periods. Plan-level rate limits protect against traffic spikes. Track every request and its cost in real time.

Per-key budgets
Spend caps
Usage tracking
Learn more
Key management
Production
active
eur_prod_****€1,000/mo
Staging
active
eur_stag_****€100/wk
Dev - Alice
active
eur_dev1_****€50/day
Legacy v1
disabled
eur_old1_****No limit
Each key has its own spend limit and reset period

Per-key spend caps

Create dedicated API keys for every project, environment, or team member. Each key can have its own spend limit with a reset period, and can be disabled or revoked instantly without affecting other keys.

  • Set a spend limit in EUR per key with daily, weekly, or monthly reset
  • Keys return 402 Payment Required when their limit is reached
  • Disable any key temporarily or revoke it permanently
  • Create separate keys for production, staging, and development

Plan-level rate limits

Your subscription plan defines rate limits that apply across all your keys. Monthly and daily request caps prevent unexpected volume, while RPM limits protect against traffic spikes.

  • Monthly request limit caps total requests per billing period
  • Daily request limit prevents concentrated usage spikes
  • Requests-per-minute cap returns 429 on bursts
  • Upgrade your plan to increase all limits as your usage grows
Plan limits (Pro)
Monthly requests
Total requests per billing period
100,000
Daily requests
Resets at midnight UTC
5,000
Rate limit
Returns 429 on excess
60 RPM
Markup
On top of provider cost
15%
Limits are set by your subscription plan
activity
847
Requests
1.2M
Tokens
200gpt-5.1scaleway1,830€0.0042
200claude-4anthropic942€0.0031
200mistral-lgmistral654€0.0008
429gpt-5.1azure-eu0€0.00
200haiku-4anthropic312€0.0004

Usage tracking

The activity dashboard shows every request with its cost, token count, model, provider, and latency. Filter by time range, model, or status to understand your spending patterns.

  • Per-request cost in EUR with input and output token breakdown
  • Filter by model, provider, status code, or time range
  • See which models and providers consume the most tokens
  • Track total requests, tokens in, and tokens out over time

Integrate AI without GDPR risk.

You need AI that won’t create compliance headaches. Your data stays in the EU, GDPR is enforced by default, and every request is routed for the best balance of cost, latency, and uptime, reducing risk while improving performance.

Get Your API Key
GDPR by default
EU data residency
Smart routing
Claim €15 free credits·300 left
Sign up free →